Models - Docs - Kiro Loading image... Product * About Kiro * IDE * CLI * Web * Mobile * Crew * Pricing * Downloads For * Enterprise * Startups * Students Community * Overview * Ambassadors * Discord * Events * Powers * Shop * Showcase Resources * Docs * Blog * Changelog * FAQs * Report a bug * Suggest an idea * Billing support Social * * * * * * * English Site Terms License Responsible AI Policy Legal Privacy Policy Cookie Preferences English Loading image... * Apps * CLI * Web * Enterprise * Pricing * Docs * Community * Resources SIGN IN DOWNLOADS Loading image... Get Started Installation Authentication Your first project Models Overview Available models Reasoning effort Features How Kiro works Specs Steering Hooks MCP Permissions Custom agents Agent Skills Powers Cloud sessions Compaction Kiroignore Checkpoints and rewind Built-in tools Configuration scopes IDE 1.x What's new in 1.0 Setup & First Run Editor Chat Experimental Troubleshooting 0.x reference CLI What's new in 3.0 Setup & First Run Terminal UI Chat Voice mode Headless mode ACP Auto complete Experimental 2.x reference Crew Quick start Installation Running 24/7 Chat Agent Capabilities Features Interfaces Apps System & storage Configuration Security Troubleshooting Web Setup & First Run Identity Center Connect your repositories Working with the agent Autonomous mode Automations Memory Configuration Sync Sandbox Mobile - Preview Overview Commands and Reference CLI commands Slash commands Built-in tools Exit codes Settings Billing Overview Managing your subscription Upgrading your plan Downgrading your plan Cancelling your plan Purchasing add-on credits Managing your payments Managing usage notifications Managing your taxes Contacting billing support Deleting your account Related questions Enterprise Concepts Onboarding quickstart Connecting your identity provider Deployment options Subscribe your team Manage subscriptions Governance Monitor and track Settings Managed updates Billing IAM Supported regions Privacy and Security Overview Data protection Code references Compliance validation Infrastructure security IAM permissions Firewalls, proxies, and data perimeters VPC endpoints (AWS PrivateLink) Guides Overview Language support Learn by playing Migration Migrating from Q Developer Migrating from VSCode Upgrading from Q CLI Copy page View as Markdown Models Copy page View as Markdown Kiro gives you access to frontier and open weight AI models from OpenAI, Anthropic, and other providers. GPT-5.6 brings OpenAI models to Kiro for the first time, with three tiers that balance agentic performance and cost. Pick the right model for the job, or select Auto to let Kiro route each task to the optimal model automatically. Info Model selection is only available for chat experience - interactive and non-interactive. Quick comparison Model Context Cost Regions Free Pro Pro+ Pro Max Power GPT-5.6 Sol 272K 2.4x US, EU ✓ ✓ ✓ ✓ GPT-5.6 Terra 272K 1.0x US, EU ✓ ✓ ✓ ✓ GPT-5.6 Luna 272K 0.1x US, EU ✓ ✓ ✓ ✓ Claude Opus 5 1M 2.2x US, EU ✓ ✓ ✓ ✓ Claude Opus 4.8 1M 2.2x US, EU ✓ ✓ ✓ ✓ Claude Opus 4.7 1M 2.2x US, EU ✓ ✓ ✓ ✓ Claude Opus 4.6 1M 2.2x US, EU ✓ ✓ ✓ ✓ Claude Opus 4.5 200K 2.2x US, EU ✓ ✓ ✓ ✓ Claude Sonnet 5 1M 1.3x US, EU ✓ ✓ ✓ ✓ Claude Sonnet 4.6 1M 1.3x US, EU ✓ ✓ ✓ ✓ Claude Sonnet 4.5 200K 1.3x US, EU ✓ ✓ ✓ ✓ ✓ Claude Sonnet 4.0 200K 1.3x US, EU ✓ ✓ ✓ ✓ ✓ Auto — 1.0x US, EU ✓ ✓ ✓ ✓ ✓ Claude Haiku 4.5 200K 0.4x US, EU ✓ ✓ ✓ ✓ DeepSeek 3.2 128K 0.25x US, EU ✓ ✓ ✓ ✓ ✓ MiniMax M2.5 200K 0.25x US, EU ✓ ✓ ✓ ✓ ✓ GLM-5 200K 0.5x US, EU ✓ ✓ ✓ ✓ ✓ MiniMax M2.1 200K 0.15x US, EU ✓ ✓ ✓ ✓ ✓ Qwen3 Coder Next 256K 0.05x US, EU ✓ ✓ ✓ ✓ ✓ US and EU are geographies, each spanning several AWS Regions rather than a single Region. All authentication methods are supported for every model. For the Regions in each geography and the endpoint that serves your requests, see Inference endpoint regions . Cost is relative to Auto (1.0x baseline). For example, a task that costs 10 credits on Auto would cost 22 credits on Opus, 4 credits on Haiku, or 0.5 credits on Qwen3 Coder Next. Info Models that share the same credit multiplier won't necessarily consume the same number of credits per task. Actual consumption depends on factors like how many tokens the model generates, internal thinking depth, and tokenizer differences. For example, Opus 4.8 uses an updated tokenizer compared to Opus 4.6, so the same prompt and response can be counted as a different number of tokens - leading to different credit costs even though both carry a 2.2x multiplier. Inference endpoint regions The geography that serves your request depends on both the model you select and the region of your Kiro profile. GPT-5.6 models are served from the US regardless of your profile region. Every other model is served from the geography that matches your profile. Profile region applies to enterprise users who sign in through IAM Identity Center or an external identity provider. Free Tier users and individual subscribers are always served from the US. Model Kiro profile in US East (N. Virginia) Kiro profile in Europe (Frankfurt) GPT-5.6 Sol US US GPT-5.6 Terra US US GPT-5.6 Luna US US Claude Opus 5 US EU Claude Opus 4.8 US EU Claude Opus 4.7 US EU Claude Opus 4.6 US EU Claude Opus 4.5 US EU Claude Sonnet 5 US EU Claude Sonnet 4.6 US EU Claude Sonnet 4.5 US EU Claude Sonnet 4.0 US EU Auto US EU Claude Haiku 4.5 US EU DeepSeek 3.2 US EU MiniMax M2.5 US EU GLM-5 US EU MiniMax M2.1 US EU Qwen3 Coder Next US EU Regions in each geography Kiro is powered by Amazon Bedrock, which uses cross-region inference to distribute requests across the Regions within a geography. Your request can be processed in any Region listed for your geography. Geography Regions used for inference US US East (N. Virginia) us-east-1 , US West (Oregon) us-west-2 , US East (Ohio) us-east-2 , AWS GovCloud (US-East), AWS GovCloud (US-West) EU Europe (Frankfurt) eu-central-1 , Europe (Ireland) eu-west-1 , Europe (Paris) eu-west-3 , Europe (Stockholm) eu-north-1 , Europe (Milan) eu-south-1 , Europe (Spain) eu-south-2 Cross-region inference does not change where your data is stored. Models marked experimental are an exception to the table above: they may be processed in commercial AWS Regions worldwide, including outside your profile's geography. See data protection for the full reference, and Amazon Bedrock cross-Region inference for how inference profiles route requests. How to switch models IDE CLI Web Mobile Use the model dropdown in the chat interface to switch models. Your selection applies to all subsequent messages in the conversation. Which model should you use? Use case Model Why General development Auto Routes to the optimal model per task, balances quality and cost automatically Hardest multi-step development GPT-5.6 Sol Best fit for long-horizon refactors and terminal work that requires sustained planning and tool coordination Routine multi-step development GPT-5.6 Terra Balanced tier for everyday agentic work; its 1.0x Kiro credit multiplier sits between Luna's 0.1x and Sol's 2.4x High-frequency agentic work GPT-5.6 Luna Fastest, lowest-cost GPT-5.6 tier for repeated tasks where throughput matters; 0.1x Kiro credit multiplier Highest reliability Opus 5 State-of-the-art on agentic coding benchmarks, strongest multi-agent coordination, completes full tasks rather than leaving stubs Near-Opus agentic at lower cost Sonnet 5 Approaches Opus 4.8 on reasoning and tool use, plans before editing, runs longer autonomously Speed or credit savings Haiku 4.5 Near-frontier intelligence at a fraction of the cost, great for quick iterations and sub-agents Frontier coding at low cost MiniMax M2.5 Near Opus-level results at 0.25x cost, strong across the full development lifecycle Repo-scale agentic work GLM-5 200K context optimized for long-horizon workflows across large codebases Long coding sessions on a budget Qwen3 Coder Next 256K context with strong error recovery at 0.05x cost Model availability Model availability can vary by country or region. Kiro's model offerings align with each provider's usage and geographic requirements. For more information, see supported countries and regions: OpenAI , Anthropic , MiniMax , Zhipu AI (GLM), DeepSeek , and Qwen . Reasoning effort For models that support configurable reasoning effort, you can control how much reasoning the model applies to your prompts. Lower effort levels produce faster, shorter responses and use fewer credits. Higher levels spend more tokens on deeper analysis, multi-step reasoning, and thorough code generation. Capability IDE CLI Web Mobile Reasoning effort selection ✓ ✓ — — Set the level from the model selector's Effort panel in the IDE, or with /effort (or the --effort launch flag) in the CLI. Your choice persists, and the picker only shows levels supported by your current model. See Reasoning effort for the full reference: per-surface mechanics, supported models, persistent per-model defaults, thinking behavior, and precedence. Info Higher effort levels use more tokens internally, which means more credit consumption per interaction - even at the same credit multiplier. This is one reason why two models with identical multipliers can produce different credit costs for the same task. Best practices * Start with Auto for most work. It optimizes both quality and cost automatically. * Use GPT-5.6 Sol for the hardest multi-step work - long-horizon refactors and complex terminal tasks where you need state-of-the-art agentic performance. * Use GPT-5.6 Terra or Luna when you want strong agentic capability with throughput or cost as the primary concern. Terra for balanced performance, Luna for maximum efficiency. * Switch to Opus 5 when you hit a wall on a complex problem, need sustained multi-file work, or want the strongest multi-agent coordination and code review accuracy. * Use Sonnet 5 when you want strong agentic behavior at a lower cost than Opus, especially for multi-step tasks that need to run to completion. * Use Haiku for quick iterations, simple fixes, or when you want to conserve credits. * Monitor your usage in your account settings to understand how model choice affects consumption. * Factor model cost into your tier: If you primarily use Opus, consider Pro+, Pro Max, or Power for more credits. See plans and billing for details. For detailed descriptions of each model's capabilities, strengths, and lifecycle status, see Available models . Page updated: August 4, 2026 Your first project Available models